Data Collection and Preprocessing Management for Sugarcane Leaf Disease Identification Using by Spatial Relation-Assisted Contrast Enhancement (SRCE)

Background: Sugarcane, an essential commodity for the global sugar industry, is very vulnerable to several illnesses that significantly impact its output and quality. Methods: The study uses Spatial Relation Assisted Contrast Enhancement (SRCE) to enhance contrast in images of harmed sugarcane leaves. SRCE selectively enhances contrast, allowing for better differentiation between healthy and diseased areas. It focuses on local neighborhoods, highlighting critical symptoms while preserving leaf structure and texture. The enhanced images were analyzed using machine learning classifiers to assess their effectiveness in disease detection. Result: The results demonstrated that SRCE significantly improved the detection accuracy compared to traditional contrast enhancement techniques. This method aids in early disease identification and supports precision agriculture practices by enabling timely interventions. The results of SRCE of CII, LIF, SSIM, and PSNR values are evaluated. Conclusion: Our findings suggest that SRCE can be a valuable agricultural monitoring and management tool, ultimately contributing to increased sugarcane yield and sustainability.